Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1121797 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1090443 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0657. Min Act: -0.0001

Data Index: 1185774 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0632. Min Act: -0.0001

Data Index: 858533 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0624. Min Act: -0.0001

Data Index: 186967 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0643. Min Act: -0.0001

Data Index: 146475 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0655. Min Act: -0.0001

Data Index: 610218 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1067425 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0639. Min Act: -0.0001

Data Index: 274894 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0611. Min Act: -0.0001

Data Index: 439342 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0628. Min Act: -0.0001

Data Index: 366010 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0585. Min Act: -0.0001

Data Index: 611727 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0592. Min Act: -0.0001

Data Index: 127975 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1300933 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1981 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0604. Min Act: -0.0001

Data Index: 802175 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0558. Min Act: -0.0001

Data Index: 432657 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0584. Min Act: -0.0001

Data Index: 803996 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0606. Min Act: -0.0001

Data Index: 656226 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0549. Min Act: -0.0001

Data Index: 737530 (C4 (Web Text))

Max Activating Token Index: 793